Flirting with Models

In this episode I speak with the anonymous twitter user @macrocephalopod. The arc of our conversation follows the arc of his career: beginning with slow-frequency style premia in a hedge fund to building a prop desk that trades mid-to-high frequency strategies in crypto. A large part of the conversation can be characterized as comparing and contrasting the roles through the lenses of research, operations, and risk management. For example, in what ways is long/short equity meaningfully different than long/short crypto? Or, how important are topics like market impact, fill ratios, and borrow fails in mid- versus slow frequency strategies? While crypto is the venue, I believe the wisdom imparted in this episode spans all markets. Please enjoy my conversation with @macrocephalopod.

My guest is Roni Israelov, CIO of NDVR. Prior to NDVR, Roni was a principal at AQR Capital Management, where he worked on global risk models, high frequency factors, and lead the development and oversight of options-oriented strategies. Taking a page from Roni’s career and research, our conversation is far ranging. We discuss topics from global asset risk models to the application of high frequency signals to tail risk hedging. While there are insights to glean in each of these topics, I think the conversation helps paint an insightful picture about how Roni thinks about research in general. Towards the end of the conversation we talk about the new research Roni is tackling at NDVR, a financial advisory firm for high net worth individuals. The role brings new challenges to consider, such as liability management and risk tolerance within the framework of portfolio optimization. Even though the topics differ, I think you’ll hear a very common thread in how the research is performed. Please enjoy my conversation with Roni Israelov.

Doug Colkitt is an ex-high frequency trader, ex-MEV bot searcher, and founder of the decentralized exchange CrocSwap. In this episode, we talk about all three. We begin with high frequency trading, where Doug walks us through the differences between maker and taker strategies, why queue position is so critical for makers, and why volatility is a high frequency trader’s best friend. We then discuss Ethereum-based MEV strategies. Doug explains what MEV is, how the architecture of the Ethereum block chain allows it to exist, and a high level topology of the different types of MEV strategies that exist. He also explains how the game theory behind MEV changed dramatically with the launch of Flashbots. Finally, we talk about his new decentralized exchange CrocSwap and its primary innovations, including dynamic fee levels, identification of toxic flow, and vaults that enable KYC. I hope you enjoy my conversation with Doug Colkitt.

My guest this episode is Jeff Yan, founder of Chameleon Trading. Jeff began his career in high frequency trading at Hudson River Trading but soon moved over to the world of crypto where he built one of the largest market making firms in the space. After Jeff gets me up to speed with the basics of high frequency market making, we dive into some of the more esoteric components, particularly with respect to centralized crypto exchanges. These include infrastructure quirks, adversarial algorithms, and why HFT P&L might actually be predictive of medium-term price movement. In the back half of the conversation, Jeff explains the problems he sees with current decentralized exchanges and introduces Hyperliquid, a new decentralized trading platform built on its own blockchain to provide performant order book execution for perpetual futures. Please enjoy my conversation with Jeff Yan.

Jason Buck is the co-founder and CIO of Mutiny Funds and maybe one of the most interesting people I know. Jason made, and subsequently lost, a fortune in commercial real estate in the 2008 crash. This “ego destroying event” was the catalyst for him to completely rethink the idea of resiliency, both in business and investments. Jason spent the better part of the 2010s developing the Cockroach portfolio, a modern take on Harry Brown’s permanent portfolio. A quarter stocks, a quarter bonds, a quarter CTA, and a quarter long volatility, Jason has designed the portfolio to provide all weather returns, with the possibility of serving as an entrepreneurial hedge. We discuss the value of tail hedging, tail hedges versus long volatility trades, the limits of manager diversification, and managed futures/CTAs versus static commodity positions. As a final note, this episode was recorded live at the Exchange ETF event in Miami. Enjoy.

There is no doubt that the tools of machine learning and the promise of artificial intelligence has captured the imagination of quantitative researchers everywhere. But I am aware of few fund managers who have wholesale adopted the ideas into their investment stack as thoroughly as Angus Cameron. In this dive back into the archives, we return to Season 4, Episode 6 where I spoke with Angus about his background as a discretionary macro trader and his evolution into a fully systematic, machine-learning driven investment stack. Not just in how signal is identified, but in how trades are structured and managed. If the idea of a swarm of AI trading bots doesn’t get you excited, this might not be the episode… or the podcast… for you!

In our industry, we’re all too often guilty of asking, “what is your alpha,” rather than, “what is your process for finding alpha?” Yet, in the long run, it is the process that is important. I’m equally guilty of this. In the history of this podcast, I’ve probably overemphasized the outcome of research versus the process of research. There are a few exceptions, though. And in this dive into the archives, I wanted to return to Season 2, when I spoke with Chris Meredith, Co-Chief Investment Officer at O’Shaughnessy Asset Management. There are a lot of nuggets in this episode, ranging from ingesting data to working with research partners to a discussion of hardware setup. But the part that has always stuck with me the most was Chris’s process for prioritizing research proposals based upon an AUM-scaled information ratio. I’ll let Chris explain. Enjoy.

In July 2020 I interviewed Cliff Asness, co-founder of AQR. This was several months after he penned a perspective piece titled The Valuesburg Address, where he waxed poetic about the multi-year drawdown in the value factor. Nearly three years later, he recently wrote the perspective piece titled, The Bubble Has Not Popped. I say wrote, but it is just a single image of the value spread between growth and value, adjusted for just about every possible noise factor you can imagine. The spread still hovers near generational highs. This isn’t Cliff’s first value drawdown. While never easy, I suspect his past experience at least makes it a bit easier. In this archive clip, I wanted to highlight the wisdom of experience. To me, that entails understanding what you know, what you wish you could know, and what you believe. I hope you enjoy.

It’s no secret that high flying growth stocks were hammered in 2022, so I thought it would be fun to revisit my conversation with Jason Thomson back in Season 3. Jason is a portfolio manager at O’Neil Global Advisors, where he manages highly concentrated portfolios of growth stocks. Now, Jason is a discretionary PM, which may seem like an unusual guest for a quant podcast. But his approach is so data and process driven, it’s hard to tell the difference. I selected a few questions about his take on growth investing in general, but I’d highly recommend you go back and listen to the original episode for his thoughts on portfolio construction and risk management as well. Enjoy!

After March 2020, a growing research interest of mine was the question, “how do strategies reflexively impact the markets they trade?” Beyond crowding risk, can adoption of strategies fundamentally change market dynamics. In Season 3 Episode 11, I spoke with Omer Cedar, who argues that equity quants have done precisely that. The mass adoption of factor models, whether for alpha or risk, fundamentally changed how baskets of stocks are bought and sold. For a discretionary manager to ignore this sea change is to ignore a fundamental shift in the current of the water they swim in. In this clip from the episode, Omer discusses how quants have changed the market and how fundamental managers should use this information to sharpen their edge.

We’re back with another clip from the archives. This time it’s Season 4 Episode 9 with Vivek Viswanathan. For three decades, equity quants have largely lived under the authoritative rule of the Fama-French 3 Factor Model and linear sorts. In this episode, Vivek provides an cogent alternative to the orthodoxy. Specifically, he explains why an unconstrained, characteristic-driven portfolio can more efficiently capture behavioral-based market anomalies. I think this is a master class for alternative thinking in quant equity. It was really tough to clip this episode. Vivek’s comments about Chinese markets provide a tremendous example about finding alpha in alternative markets. But I’ll leave that for you to go back and dig out! Okay, let’s dive in.

We’re rewinding to Season 3, Episode 3 to chat with Benn Eifert, founder of QVR. Benn was my first repeat guest and this is probably one of our more popular episodes. Instead of the usual interview format, I called this episode “Bad Ideas with Benn Eifert,” and basically just asked him a bunch of questions about naive option trades and whether they are a good idea or not. For anyone starting their journey with options or volatility, the whole episode is a must listen. The clips I chose here were selected because I thought they provided a really good cross-section of topics in the world of options while highlighting one important common thread: the risk of unintended bets. I think this is one of the most universally important concepts in trading and investing, and Benn really drives the points home here as we cover topics ranging from writing options for income to why VIX minus realized doesn’t mean what you think it does. The subtle through line is the reminder that it’s what we don’t know we don’t know that will eventually get us in trouble.

We’re trying something new here, folks. I’ve got 5 seasons and 60 brilliant episodes and I thought it would be fun, in the off season, to go back to the archives and highlight past conversations. So using my trusty random number generator, I chose an episode at random. So, we’re going back to 2018 to my conversation with John Alberg, co-founder of Euclidean Technologies, where machine learning is applied to the value investing problem. The part I’m highlighting starts around minute 20 and is about the formulation of the machine learning problem and how the research question should be asked. I like this section because I think it really highlights how we can think about the tradeoff of degrees of complexity versus accuracy and the problem of overfitting. Enjoy!

In this episode I speak with Giuliana Bordigoni, Director of Specialist Strategies at Man AHL. In her role, Giuliana oversees the firm’s strategies that require specialist knowledge. This includes, for example, alternative markets, options trading, credit, and machine learning. We spend a good deal of time discussing alternative markets, a focus of Giuliana’s in both her current role and her prior as the Head of Alternative Markets. We discuss the potential benefits and challenges of introducing alternative markets to existing CTA programs, unexpected roadblocks in doing so, and the opportunities that Giuliana is most excited about today. We also discuss machine learning, which is treated as its own unique class of strategy rather than as a technique, and why Giuliana is so excited about systematic credit today. I hope you enjoy my conversation with Giuliana Bordigoni.

In this episode I speak with Adam Butler, co-founder and CIO of ReSolve Asset Management. For full disclosure, at the time of recording I am personally an investor in one of ReSolve’s private funds. Adam last joined the show in Season 1, where we discussed his background and philosophy of diversification. This episode begins with a discussion of how Adam’s thinking and process has evolved over the last four-plus years, much of which is centered around the idea of experimental design. Adam discusses the adoption of machine learning techniques, the spectrum of complexity between zero- and strong-prior signals, and how proper experiment design allows for greater process diversification. The back half of the conversation dances across a few subjects. We discuss topics such as seasonality, carry, the operational burdens of introducing a full-stack machine learning process, and the difficulties allocators face in introducing multi-strategy alternatives into their portfolios. I hope you enjoy this episode with Adam Butler.

In this episode I speak with Kevin Cole, CEO and CIO of Campbell & Company. In the first half of the conversation, we discuss Campbell’s flagship systematic multi-strategy program. We cover topics including trend-following versus multi-strategy, the taxonomy of alpha signals, the concept of edge when you’re running hundreds of models, the process for introducing and sunsetting signals, and risk management. With such a strong focus on quantitative research, we spend the latter half of the conversation discussing how Campbell organizes its research team and process. Kevin explains how the team is organized and how the agenda is set. He also introduces the management process they’ve adopted called “Pulse,” providing the framework for which the team operates. Please enjoy my conversation with Kevin Cole.

Today I am joined by Hari Krishnan, Head of Volatility Strategies at SCT Capital and author of the books Second Leg Down and Market Tremors. We begin with a discussion of Hari’s newest book, Market Tremors, and the main theoretical idea: Mean Field Theory. Hari lays out both the philosophical underpinnings of the concept as well as how one might interpret it in practice. This leads into a natural discussion of dominant agents, including examples of who they are, how we might go about identifying them, and why they are so important to consider. In the back half of the conversation, we tackle some more practical considerations of tail risk hedging. This includes key differences between equity and rates markets, how we might structure hedges in today’s market environment, how to navigate path dependency, and why it’s all just a “bag of tricks.” Please enjoy my conversation with Hari Krishnan.

In this episode I speak with Harel Jacobson, an FX volatility trader. There is a lot that makes the FX volatility market unique. For starters, the end users are more focused on hedging cash-flow and liquidity than wealth. Since the underlying is currency pairs, volatility surface arbitrage conditions become multi-dimensional. And then there is the global geopolitical event calendar to consider. Did I mention that trades are performed, almost exclusively, OTC? So even something like price discovery, which we take for granted on listed exchanges, is non-trivial. Especially if you want to backtest a new research idea. This is a fascinating conversation into a fairly niche, but important global market. I hope you enjoy my conversation with Harel Jacobson.

My guest in this episode is Andrew Beer, co-founder of Dynamic Beta Investments. Andrew has spent the last 15 years trying to pioneer the adoption of hedge fund replication strategies. The core thesis is that several hedge fund categories can be dynamically replicated using just a handful of liquid market exposures and some regression techniques. He argues that if he can deliver the strategy beta while cutting out hundreds of basis points of management fees and trading costs, it would consistently earn him a top decile rank. And all this can be done in a daily liquid vehicle. The Devil, of course, is in the details. Which categories can be replicated is an important consideration. Whether to perform a bottom-up or top-down replication is another. And, obviously, which factors to incorporate. Andrew stresses that the answer to all these questions comes not from quantitative analysis, but from a qualitative understanding of how hedge fund managers actually operate. This episode may not be as technical as others, but it certainly had me walking away thinking, “if there’s no points for originality, it certainly seems a lot easier to just copy the work of others. Especially if I can cut out all their fees.” Please enjoy my episode with Andrew Beer.

My guest in this episode needs no introduction: Antti Ilmanen, co-head of Portfolio Solutions at AQR, award winning researcher, and author of the books Expected Returns and the recently published Investing Amid Low Expected Returns. A decade has passed since Antti wrote his first book, providing both a decade of out-of-sample data as well as a decade of new research. I begin by asking Antti about where his conviction has hardened and the things he’s changed his mind about. From there, however, the conversation topics become much more wide ranging. We discuss structural changes in the market, the growth of passive investing, and his research on who is actually on the other side of style premia trades. We then discuss trend following versus put protection, trend following’s difficult decade, and why the outlook for trend may be rosier going forward. Finally, we touch upon some more practical topics, addressing low-hanging opportunities Antti has seen in his role as co-head of Portfolio Solutions at AQR. I hope you enjoy my conversation with Antti Ilmanen.